Deep Residual Networks (ResNets) are prone to overfitting in problems with uncertainty, such as intrusion detection problems. To alleviate this problem, we proposed a method that combines the Adaptive Neuro-fuzzy Inference System (ANFIS) and the ResNet algorithm. This method can make use of the advantages of both the ANFIS and ResNet, and alleviate the overfitting problem of ResNet. Compared with the original ResNet algorithm, the proposed method provides overlapped intervals of continuous attributes and fuzzy rules to ResNet, improving the fuzziness of ResNet. To evaluate the performance of the proposed method, the proposed method is realized and evaluated on the benchmark NSL-KDD dataset. Also, the performance of the proposed method is compared with the original ResNet algorithm and other deep learning-based and ANFIS-based methods. The experimental results demonstrate that the proposed method is better than that of the original ResNet and other existing methods on various metrics, reaching a 98.88% detection rate and 1.11% false alarm rate on the KDDTrain+ dataset.
As one fundamental data-mining problem, ANN (approximate nearest neighbor search) is widely used in many industries including computer vision, information retrieval, and recommendation system. LSH (Local sensitive hashing) is one of the most popular hash-based approaches to solve ANN problems. However, the efficiency of operating LSH needs to be improved, as the operations of LSH often involve resource-consuming matrix operations and high-dimensional large-scale datasets. Meanwhile, for resource-constrained devices, this problem becomes more serious. One way to handle this problem is to outsource the heavy computing of high-dimensional large-scale data to cloud servers. However, when a cloud server responsible for computing tasks is untrustworthy, some security issues may arise. In this study, we proposed a cloud server-aided LSH scheme and the application model. This scheme can perform the LSH efficiently with the help of a cloud server and guarantee the privacy of the client’s information. And, in order to identify the improper behavior of the cloud server, we also provide a verification method to check the results returned from the cloud server. Meanwhile, for the implementation of this scheme on resource-constrained devices, we proposed a model for the real application of this scheme. To verify the efficiency and correctness of the proposed scheme, theoretical analysis and experiments are conducted. The results of experiments and theoretical analysis indicate that the proposed scheme is correct, verifiable, secure and efficient.
21 February 2026 in International Journal of Pattern Recognition and Artificial Intelligence
Intrusion detection is a fuzzy classification problem. Intrusion detection can detect the attack behaviors of hackers in advance. For generating a visualizing architecture for identifying intrusions, this study proposes an approach that combines ANFIS (Adaptive Network-based Fuzzy Inference System), DT (Decision Tree), and K-means clustering algorithm for visualizing the deep pattern of intrusion detection. The ANFIS generates complex and fuzzy combinations of selected attributes. To reduce the rules generation of ANFIS, Pearson Correlation analysis is used to select attributes that highly relate to the target. Meanwhile, standard deviation analysis and a proposed adaptive K-means algorithm are used for determining the interval division of selected attributes. Then, the CART (classification and regression tree) is used to identify the deep mode in generated rules and selected attributes. The architecture of the proposed algorithm is a hybrid visualizing approach. The architecture can identify deep and hybrid features in intrusion detection. The proposed algorithm was trained, validated, and tested on the NSL-KDD dataset. Using 22 attributes that highly relate to the target, the performance of the proposed method achieved a 99.86% detection rate and 0.14% false alarm rate, which is better than many classifiers. Besides, the visualizing model can help us visually identify the complex pattern of intrusions and analyze the pattern of various intrusions.
To address the challenges of data silos across different institutions, privacy concerns, and the multi-party genomic data matching problem in crop breeding, this paper proposes a Fed-LSH framework. This framework is a collaborative framework integrating privacy- enhanced Locality-Sensitive Hashing (LSH) algorithm with Federated Learning. It enables participants can conduct cross- institutional similar genomic association analysis and elite allele identification, And they do not need to share raw genomic data with each other. This framework utilizes distributed hash index construction, outsourced computation, and encrypted similarity search to accomplish this task. Experiments show that Fed-LSH can achieve a hit rate of 60.72% ± 1.2% when recommending 4 candidates, using a 40×3 hash size on 3072-dimensional data (implemented on standard personal computers). It can select 4 candidates from 10,000 genomic fragments (each 3072-dimensional) in less than 0.5 seconds. These performance metrics indicate that Fed-LSH provides foundational technical support for privacy-preserving collaborative tomato breeding.